© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 3582
    Prev
    Next
    INDEX
    Explanations

    legal and investigative terminology related to establishing cause for actions or events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to probability and probable cause

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uart
    -0.96
    artney
    -0.91
    agra
    -0.91
    ravings
    -0.84
    hetti
    -0.82
    ophon
    -0.81
    helle
    -0.80
    afort
    -0.78
    emark
    -0.77
    atcher
    -0.73
    POSITIVE LOGITS
     assumption
    0.83
    hood
    0.82
     probability
    0.82
    ties
    0.81
     inference
    0.79
     prediction
    0.76
     scenario
    0.76
     cause
    0.73
     occurrence
    0.72
     signature
    0.71
    Activations Density 0.062%

    No Known Activations